Full-stack engineer specializing in LLM orchestration, RAG pipelines, and agentic workflows. Shipping production AI systems, cross-platform apps, and scalable backend services.
Status
Open to new work
Full-stack engineer shipping production AI systems, cross-platform mobile apps, and scalable backend services. Specialized in LLM orchestration, RAG pipelines, and agentic workflows — with a track record of owning features end-to-end across React Native, Flutter, FastAPI, Fastify, and AWS. Comfortable operating at the intersection of production AI and product engineering.
Five stops, mostly remote. Each one stamped.
Lead Product Engineer
January 2024 — March 2025 · Turkey · Remote
Things I built because I wanted them to exist.
a multi-agent coding harness
Breaks a goal into a graph of tasks and runs each one with a coding agent (Claude Code, Codex, Gemini CLI, or a model on NVIDIA NIM) in its own git worktree. A task merges only when its checks pass, an optional reviewer agent approves, and the checks pass again on the merged tree; a merge that breaks the tree is rolled back, and conflicts go to a narrow resolver agent that keeps both sides. Work lands on an integration branch, never your own, and an interrupted run resumes where it stopped. Ships as a CLI, a live dashboard, and a Tauri desktop app for macOS and Windows.
an AI that joins your Google Meet
Send a meeting link to a Telegram bot and Tekki shows up in the call as its own participant, listens, thinks, and answers out loud with a face that reacts. Google Meet has no bot API, so it becomes the devices instead: getUserMedia is replaced inside the page and handed a canvas for video and a WebAudio node for audio. Hearing works the other way round — Chrome never returns decoded WebRTC audio to WebAudio, so the container records its own PulseAudio sink. Every model runs locally; nothing about the conversation leaves the machine.
Autonomous reasoning engine on LangGraph with a recursive Generator-Critic loop, cutting hallucinations through self-correcting multi-agent feedback. Lifelong-learning memory system built on ChromaDB (Vector RAG) and DSPy BootstrapFewShot enables runtime self-improvement without retraining, with a human-in-the-loop Chainlit interface where user critiques propagate directly into vector memory.
Chat application with AI-driven sentiment analysis to suggest replies and analyze user emotions. Built a responsive cross-platform interface using Flutter with real-time messaging.
User/Order microservices with real-time monitoring, implementing fault tolerance via Circuit Breaker and retry mechanisms. Utilized Docker for containerization with Fluentd/Prometheus for log collection and chaos testing.
Minimalist typing speed test built from scratch with vanilla JavaScript. Supports three test modes (words, timed, and quote) with a floating real-time caret, live WPM and accuracy tracking, and a post-test performance chart rendered on the Canvas API with no charting libraries. Features a 1,500-word pool, per-keystroke error display, 30-result local history, and full keyboard navigation.
What's in the carry-on.
2021 — 2025
B.Tech, Computer Science and Engineering (CGPA: 8.41/10)
Have a project in mind or want to collaborate? I'm always open to new opportunities.
gauransh@gauranshsharma.com